sales-fireflies
Fireflies.ai platform help — AI meeting note-taker with GraphQL API, webhooks (V1 + V2), AskFred AI, real-time events, and Fred bot that joins Zoom/Meet/Teams to transcribe. Use when Fireflies transcripts not syncing to CRM, webhooks not firing or signatures failing HMAC verification, hitting 50 req/day or 60 req/min rate limits on the GraphQL API, building a transcript pipeline from Fireflies to Snowflake/BigQuery/warehouse, migrating from Webhooks V1 to V2, the Fireflies bot not joining calls or users wanting to disable auto-join, deciding between Free, Pro ($10), Business ($19), or Enterprise ($39) tier, or wiring AskFred or Real-time API into an internal app. Do NOT use for comparing Fireflies vs Fathom/Avoma/Gong or selecting a note-taker (use /sales-note-taker) or reviewing a single sales call for coaching (use /sales-call-review).
What this skill does
# Fireflies.ai Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated platform knowledge.
Ask the user:
1. **What's your goal?**
- A) API integration (transcripts → CRM, warehouse, Slack, internal app)
- B) Webhook setup or signature verification (V1 or V2)
- C) Plan selection / pricing decision (Free, Pro, Business, Enterprise)
- D) Bot / auto-join behavior (Fred joining or missing meetings, auto-join toggles)
- E) AskFred AI, Real-time API, or MCP usage
- F) Troubleshooting a specific error (auth_failed, rate limit, missing webhook)
2. **Who owns the meetings?**
- A) Individual user (personal API key)
- B) Team-wide (Enterprise Super Admin required for team webhooks)
3. **If API integration, destination?**
- A) CRM (HubSpot, Salesforce) native sync
- B) Warehouse (Snowflake, BigQuery, Redshift)
- C) Slack / notifications
- D) Custom app or database
Skip-ahead rule: if the prompt already has enough context, skip to Step 2.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Comparing Fireflies vs Fathom/Avoma/Gong/Otter, picking a note-taker | Run: `/sales-note-taker {user's original question}` |
| Reviewing a specific call for coaching or scoring | Run: `/sales-call-review {user's original question}` |
| Building a coaching program from call data | Run: `/sales-coaching {user's original question}` |
| General CRM integration patterns (iPaaS, Zapier, webhooks) across tools | Run: `/sales-integration {user's original question}` |
Otherwise, answer directly below.
## Step 3 — Fireflies platform reference
**Read `references/platform-guide.md`** for the full platform reference — modules, pricing, integrations, GraphQL data model, common workflows (CRM sync, warehouse pipeline, HMAC verification, Webhooks V2 migration).
**Read `references/fireflies-api-reference.md`** for verbatim GraphQL docs — every query, mutation, webhook schema, and SDK example. Grep for the specific operation you need (e.g., `transcripts(` or `uploadAudio` or `meeting.summarized`) rather than loading the whole file.
Answer the user's question using only the relevant section. Don't dump the full reference.
## Step 4 — Actionable guidance
You no longer need the platform guide — focus on the user's specific situation.
- **API design rule of thumb**: GraphQL means you can request exactly the fields you need. Don't fetch `transcript.sentences` + `audio_url` + `summary` for 100 meetings in one query — GraphQL complexity limits bite. Fetch metadata in one query, then fetch transcripts per-meeting in response to webhooks.
- **Webhook choice**: For new integrations, use Webhooks V2 (`meeting.transcribed` + `meeting.summarized` events, granular subscription). V1 still works but only fires one event and uses a different payload shape.
- **Rate-limit sizing**: Free/Pro = 50 req/day — barely enough for backfills. Business/Enterprise = 60 req/min — the only realistic tier for a production pipeline. Anything beyond that needs queue-and-retry.
- **Team-wide webhooks** require Enterprise + Super Admin role. Without those, each user must configure their own webhook — doesn't scale.
If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there with today's date.
## Gotchas
*Best-effort from research — review plan-gated features and integration details before quoting to a customer.*
- **Webhooks fire only for meeting owners** (`organizer_email`). If a non-owner attendee recorded the meeting via Fred, no webhook fires for them. Team-wide webhooks exist but require **Enterprise + Super Admin**.
- **V1 and V2 webhooks coexist.** Both use `X-Hub-Signature` with `sha256=<hex>` format, but V1 has one event (`Transcription completed`) with `meetingId/eventType` payload, while V2 supports `meeting.transcribed` and `meeting.summarized` with `meeting_id/event/timestamp`. Don't mix consumers.
- **`meeting.transcribed` ≠ `meeting.summarized`.** Transcript is ready before the AI summary is. Subscribe to both if you need action items / notes — or accept a 1-3 minute delay and fetch summary by polling after transcript.
- **Free and Pro tiers are capped at 50 API requests per day.** A single backfill of 500 historical meetings will hit this hard. Upgrade to Business or Enterprise for a 60 req/min ceiling.
- **Add to Live is 3 req per 20 min**, Share Meeting is 10 req/hour (up to 50 emails per request) — these are separate from the standard GraphQL limits.
- **Upload limits**: 200MB audio for all tiers; 100MB video on Free, 1.5GB video on paid tiers.
- **Bot auto-join complaints are common** — granting calendar access makes Fred auto-join every scheduled call. Users frequently ask how to disable this; point them to the Fireflies dashboard's Auto-join settings (calendar-level and meeting-level).
- **API key is user-scoped** — it only accesses meetings that user recorded or that were shared to them. For a shared team pipeline, use Super Admin.
- **10-second webhook response SLA** on V2. Non-2xx or a timeout marks delivery failed. Do not do heavy processing inside the webhook handler — enqueue and ack immediately.
## Related skills
- `/sales-note-taker` — Note-taker selection + cross-vendor integration patterns (Fathom, Fireflies, Avoma, Gong, Otter, Fellow, Grain, Sembly, Read.ai)
- `/sales-fathom` — Fathom platform help (REST API, Svix HMAC, OAuth, SDKs, MCP, pricing)
- `/sales-call-review` — Review a specific call for coaching
- `/sales-coaching` — Build coaching programs that consume call data
- `/sales-integration` — General CRM/tool integration patterns (Zapier, webhooks, iPaaS)
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install: `npx skills add sales-skills/sales --skill sales-do`
## Examples
### Example 1: Transcripts not arriving in Snowflake after webhook event
**User says**: "My Fireflies webhook fires, but the transcript body is empty when I fetch it. What's wrong?"
**Skill does**:
1. Recognizes the classic "transcribed ≠ summarized" race — V1 webhook fires the moment ASR completes, often before AskFred summary is generated
2. Recommends migrating to Webhooks V2 and subscribing to `meeting.summarized` instead of (or in addition to) `meeting.transcribed` — then fetch transcript after summary event
3. Alternative: keep V1 and re-fetch from `transcript(id: ...)` query 60-180s after the webhook, with exponential backoff
4. Notes that V2 also gives timing-safe signature comparison headers (`sha256=<hex>` on `X-Hub-Signature`) — points to the Node/Python examples in `references/fireflies-api-reference.md`
**Result**: Root-caused the empty-transcript race, with two concrete fixes.
### Example 2: Picking a tier for a 30-person sales team with warehouse pipeline
**User says**: "We have 30 reps doing ~50 calls/week and want every transcript in BigQuery within 5 min. Which Fireflies tier?"
**Skill does**:
1. Rules out Free ($0) and Pro ($10/seat) — both capped at **50 API requests per day**, would break on day one of backfill
2. Recommends Business ($19/seat) for the 60 req/min ceiling, unlimited storage, and video recording
3. Flags that **team-wide webhooks require Enterprise + Super Admin** ($39/seat) — without it, each rep has to configure their own webhook
4. Suggests Enterprise if compliance (HIPAA, custom retention) or SSO/SCIM matters, otherwise Business with a shared team API key from the super-admin
5. Architecture sketch: Webhooks V2 `meeting.summarized` → Cloud Run → `transcripts(id: ...)` query → raw JSON to GCS + normalized rows to BigQuery via scheduled load
**Result**: Tier recommendation grounded in both pricing and the team-webhook gotcha.
### Example 3: Fred bot joining meetings nobody invited him to
**User says**: "Fireflies keeps joining meetings I didn't ask it to. How do I stop this?"
**Skill does**:
1. Explains the behavior — granting calendar access caRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.